Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1443405 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0998. Min Act: -0.0000

Data Index: 27005 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1143945 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0274. Min Act: -0.0000

Data Index: 396505 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.9860. Min Act: -0.0000

Data Index: 844900 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8146. Min Act: -0.0000

Data Index: 275563 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1450046 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1556867 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1596154 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.9031. Min Act: -0.0000

Data Index: 514599 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.9138. Min Act: -0.0000

Data Index: 217495 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1035642 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0179. Min Act: -0.0000

Data Index: 851503 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0218. Min Act: -0.0000

Data Index: 176189 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1587481 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8465. Min Act: -0.0000

Data Index: 159703 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1308127 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1030065 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.7906. Min Act: -0.0000

Data Index: 849410 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.8587. Min Act: -0.0000

Data Index: 695198 (The Pile)

Max Activating Token Index: 424